Abstract:Content-based audio information retrieval is one of the most interesting and fast-growing research areas.Suitable feature sets can help to reduce the tedious computation time and speed up retrieval. In this paper we report a study of the music spectral properties aimed at the acoustic-based music data similarity measurement and show that the spectral features of adjacent frames are highly correlated. Based on such a case study we mainly focus on making an evaluation of feature choice in the three aspects: stor… Show more
“…However, in their method, each segment is the same length. On the other hand, there is a method that divides music pieces into frames, and extracts features by merging the frames from the music pieces [10]. This is similar to our method in that it deals with similarity between the frames.…”
In this paper, we propose a music retrieval method based on the distributions of features in the music. In common music retrieval methods, if several features are similar between the query and the retrieval target, the retrieval systems return that the query is similar to the retrieval target. However, a problem is that several features in the music are ignored. If the other features in the query and the retrieval target are quite different, the query and the retrieval target should be treated as different types of music. Therefore, we calculate the importance of each feature in the music. Then, we compare the importance of features between the query and the retrieval target, and we can retrieve the music without ignoring the importance of several features. In our experimental evaluation, we can confirm that our proposed system has better accuracy than the baseline method.
“…However, in their method, each segment is the same length. On the other hand, there is a method that divides music pieces into frames, and extracts features by merging the frames from the music pieces [10]. This is similar to our method in that it deals with similarity between the frames.…”
In this paper, we propose a music retrieval method based on the distributions of features in the music. In common music retrieval methods, if several features are similar between the query and the retrieval target, the retrieval systems return that the query is similar to the retrieval target. However, a problem is that several features in the music are ignored. If the other features in the query and the retrieval target are quite different, the query and the retrieval target should be treated as different types of music. Therefore, we calculate the importance of each feature in the music. Then, we compare the importance of features between the query and the retrieval target, and we can retrieve the music without ignoring the importance of several features. In our experimental evaluation, we can confirm that our proposed system has better accuracy than the baseline method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.